Hugging Face's logo

gchhablani
/
fnet-large-finetuned-sst2

Text Classification Transformers PyTorch TensorBoard
English fnet generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
1
gchhablani commited on
Commit
31092f0
•
1 Parent(s): 814ae32

Update checkpoints

Browse files
Files changed (44) hide show
  1. README.md +76 -0
  2. all_results.json +14 -0
  3. checkpoint-16838/config.json +33 -0
  4. checkpoint-16838/optimizer.pt +3 -0
  5. checkpoint-16838/pytorch_model.bin +3 -0
  6. checkpoint-16838/rng_state.pth +3 -0
  7. checkpoint-16838/scheduler.pt +3 -0
  8. checkpoint-16838/special_tokens_map.json +1 -0
  9. checkpoint-16838/tokenizer.json +0 -0
  10. checkpoint-16838/tokenizer_config.json +1 -0
  11. checkpoint-16838/trainer_state.json +31 -0
  12. checkpoint-16838/training_args.bin +3 -0
  13. checkpoint-33676/config.json +33 -0
  14. checkpoint-33676/optimizer.pt +3 -0
  15. checkpoint-33676/pytorch_model.bin +3 -0
  16. checkpoint-33676/rng_state.pth +3 -0
  17. checkpoint-33676/scheduler.pt +3 -0
  18. checkpoint-33676/special_tokens_map.json +1 -0
  19. checkpoint-33676/tokenizer.json +0 -0
  20. checkpoint-33676/tokenizer_config.json +1 -0
  21. checkpoint-33676/trainer_state.json +46 -0
  22. checkpoint-33676/training_args.bin +3 -0
  23. checkpoint-50514/config.json +33 -0
  24. checkpoint-50514/optimizer.pt +3 -0
  25. checkpoint-50514/pytorch_model.bin +3 -0
  26. checkpoint-50514/rng_state.pth +3 -0
  27. checkpoint-50514/scheduler.pt +3 -0
  28. checkpoint-50514/special_tokens_map.json +1 -0
  29. checkpoint-50514/tokenizer.json +0 -0
  30. checkpoint-50514/tokenizer_config.json +1 -0
  31. checkpoint-50514/trainer_state.json +61 -0
  32. checkpoint-50514/training_args.bin +3 -0
  33. config.json +33 -0
  34. eval_results.json +9 -0
  35. pytorch_model.bin +3 -0
  36. runs/Sep24_12-16-35_patrick-general-gpu/1632485815.4394088/events.out.tfevents.1632485815.patrick-general-gpu.1069019.1 +3 -0
  37. runs/Sep24_12-16-35_patrick-general-gpu/events.out.tfevents.1632485815.patrick-general-gpu.1069019.0 +3 -0
  38. runs/Sep24_12-16-35_patrick-general-gpu/events.out.tfevents.1632500341.patrick-general-gpu.1069019.2 +3 -0
  39. special_tokens_map.json +1 -0
  40. tokenizer.json +0 -0
  41. tokenizer_config.json +1 -0
  42. train_results.json +8 -0
  43. trainer_state.json +70 -0
  44. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - glue
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: fnet-large-finetuned-sst2
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: GLUE SST2
19
+ type: glue
20
+ args: sst2
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9048165137614679
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # fnet-large-finetuned-sst2
31
+
32
+ This model is a fine-tuned version of [google/fnet-large](https://huggingface.co/google/fnet-large) on the GLUE SST2 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.5240
35
+ - Accuracy: 0.9048
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 2e-05
55
+ - train_batch_size: 4
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 3.0
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
66
+ | 0.394 | 1.0 | 16838 | 0.3896 | 0.8968 |
67
+ | 0.2076 | 2.0 | 33676 | 0.5100 | 0.8956 |
68
+ | 0.1148 | 3.0 | 50514 | 0.5240 | 0.9048 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.11.0.dev0
74
+ - Pytorch 1.9.0
75
+ - Datasets 1.12.1
76
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9048165137614679,
4
+ "eval_loss": 0.5239545702934265,
5
+ "eval_runtime": 19.0697,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 45.727,
8
+ "eval_steps_per_second": 5.716,
9
+ "train_loss": 0.23881868657776187,
10
+ "train_runtime": 14505.0544,
11
+ "train_samples": 67349,
12
+ "train_samples_per_second": 13.929,
13
+ "train_steps_per_second": 3.483
14
+ }
checkpoint-16838/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "sst2",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "positive": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
checkpoint-16838/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a7289f2f2917083eb2ec844bff6b918b1f6fc0a5a37e08f5acb153cd0d024b
3
+ size 1895696981
checkpoint-16838/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444cd337752ee912244e41c19d765568f5336754da22d912cf3e46cb31e42985
3
+ size 947877033
checkpoint-16838/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff4d8efc54045f93675f588d8af1a465fc39f1f1d547c72b3aaeaae6a4abded
3
+ size 14503
checkpoint-16838/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae66c884bb33823868cb811e759ca1de834181799cc0072609abd7b9ad7aa91
3
+ size 623
checkpoint-16838/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
checkpoint-16838/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-16838/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-16838/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 16838,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.394,
14
+ "step": 16838
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8967889908256881,
19
+ "eval_loss": 0.3896108567714691,
20
+ "eval_runtime": 19.0439,
21
+ "eval_samples_per_second": 45.789,
22
+ "eval_steps_per_second": 5.724,
23
+ "step": 16838
24
+ }
25
+ ],
26
+ "max_steps": 50514,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 4.213461867364147e+16,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-16838/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb72553013dd35026c47f6f4467bb571ac0675d6549f1a069d3d19b0c3a66e86
3
+ size 2735
checkpoint-33676/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "sst2",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "positive": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
checkpoint-33676/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4394bacab91d9b5862d475bf2a8767a0bd3c5a79182d2178c84b61a3039cdd
3
+ size 1895696981
checkpoint-33676/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0464e206160c6380fb98b470a1ba6232eeb2ec4cf5fde9496451b96646ef7bc
3
+ size 947877033
checkpoint-33676/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b58dab6a05d21f8714b1448dbd1d86d23e1db99fc84ee77e74119b6b23b62f
3
+ size 14503
checkpoint-33676/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8e383a96a8477d2d931b1a89e7d5d2676902b87fc0b4a137fe0efa48a132c1
3
+ size 623
checkpoint-33676/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
checkpoint-33676/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-33676/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-33676/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 33676,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.394,
14
+ "step": 16838
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8967889908256881,
19
+ "eval_loss": 0.3896108567714691,
20
+ "eval_runtime": 19.0439,
21
+ "eval_samples_per_second": 45.789,
22
+ "eval_steps_per_second": 5.724,
23
+ "step": 16838
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.2076,
29
+ "step": 33676
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8956422018348624,
34
+ "eval_loss": 0.5100129246711731,
35
+ "eval_runtime": 19.0123,
36
+ "eval_samples_per_second": 45.865,
37
+ "eval_steps_per_second": 5.733,
38
+ "step": 33676
39
+ }
40
+ ],
41
+ "max_steps": 50514,
42
+ "num_train_epochs": 3,
43
+ "total_flos": 8.426923734728294e+16,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-33676/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb72553013dd35026c47f6f4467bb571ac0675d6549f1a069d3d19b0c3a66e86
3
+ size 2735
checkpoint-50514/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "sst2",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "positive": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
checkpoint-50514/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b64a8365fcbb220d48dd9918cdb17c1becc94b844ae66b2df45e78208013194
3
+ size 1895696981
checkpoint-50514/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a4a707ec45dda50ae24c48ab665b1c512b7af48039f293ad622939063c4d82
3
+ size 947877033
checkpoint-50514/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becedb8d488278c5c8e77dbd4aebdb92b237eccc219fda9b39598148c7a7de40
3
+ size 14503
checkpoint-50514/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c1c9b0b18973347a64b1087646863f54fde9f321e4adaad62d84eb0b11f7dc
3
+ size 623
checkpoint-50514/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
checkpoint-50514/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-50514/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-50514/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 50514,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.394,
14
+ "step": 16838
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8967889908256881,
19
+ "eval_loss": 0.3896108567714691,
20
+ "eval_runtime": 19.0439,
21
+ "eval_samples_per_second": 45.789,
22
+ "eval_steps_per_second": 5.724,
23
+ "step": 16838
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.2076,
29
+ "step": 33676
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8956422018348624,
34
+ "eval_loss": 0.5100129246711731,
35
+ "eval_runtime": 19.0123,
36
+ "eval_samples_per_second": 45.865,
37
+ "eval_steps_per_second": 5.733,
38
+ "step": 33676
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.1148,
44
+ "step": 50514
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.9048165137614679,
49
+ "eval_loss": 0.5239545702934265,
50
+ "eval_runtime": 18.9842,
51
+ "eval_samples_per_second": 45.933,
52
+ "eval_steps_per_second": 5.742,
53
+ "step": 50514
54
+ }
55
+ ],
56
+ "max_steps": 50514,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 1.2640385602092442e+17,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-50514/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb72553013dd35026c47f6f4467bb571ac0675d6549f1a069d3d19b0c3a66e86
3
+ size 2735
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "sst2",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "negative",
14
+ "1": "positive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "negative": 0,
20
+ "positive": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9048165137614679,
4
+ "eval_loss": 0.5239545702934265,
5
+ "eval_runtime": 19.0697,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 45.727,
8
+ "eval_steps_per_second": 5.716
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a4a707ec45dda50ae24c48ab665b1c512b7af48039f293ad622939063c4d82
3
+ size 947877033
runs/Sep24_12-16-35_patrick-general-gpu/1632485815.4394088/events.out.tfevents.1632485815.patrick-general-gpu.1069019.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110e9cee7384b81d73bd6378a712fe6e18362e3184155cf9cc4fd63085e922e8
3
+ size 4349
runs/Sep24_12-16-35_patrick-general-gpu/events.out.tfevents.1632485815.patrick-general-gpu.1069019.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfdfa9d92d3ab0cf9eb7f8118f936fd16e1aef1bb2fb84499f9ed3b33a82e03
3
+ size 4994
runs/Sep24_12-16-35_patrick-general-gpu/events.out.tfevents.1632500341.patrick-general-gpu.1069019.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3187ab8c063cb2bad5747b2c00a7946e9f93037965760ba2d58b2adee5b3883f
3
+ size 369
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.23881868657776187,
4
+ "train_runtime": 14505.0544,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 13.929,
7
+ "train_steps_per_second": 3.483
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 50514,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.394,
14
+ "step": 16838
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8967889908256881,
19
+ "eval_loss": 0.3896108567714691,
20
+ "eval_runtime": 19.0439,
21
+ "eval_samples_per_second": 45.789,
22
+ "eval_steps_per_second": 5.724,
23
+ "step": 16838
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.2076,
29
+ "step": 33676
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8956422018348624,
34
+ "eval_loss": 0.5100129246711731,
35
+ "eval_runtime": 19.0123,
36
+ "eval_samples_per_second": 45.865,
37
+ "eval_steps_per_second": 5.733,
38
+ "step": 33676
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.1148,
44
+ "step": 50514
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.9048165137614679,
49
+ "eval_loss": 0.5239545702934265,
50
+ "eval_runtime": 18.9842,
51
+ "eval_samples_per_second": 45.933,
52
+ "eval_steps_per_second": 5.742,
53
+ "step": 50514
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "step": 50514,
58
+ "total_flos": 1.2640385602092442e+17,
59
+ "train_loss": 0.23881868657776187,
60
+ "train_runtime": 14505.0544,
61
+ "train_samples_per_second": 13.929,
62
+ "train_steps_per_second": 3.483
63
+ }
64
+ ],
65
+ "max_steps": 50514,
66
+ "num_train_epochs": 3,
67
+ "total_flos": 1.2640385602092442e+17,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb72553013dd35026c47f6f4467bb571ac0675d6549f1a069d3d19b0c3a66e86
3
+ size 2735